Next Article in Journal
Previous Article in Journal
Int. J. Mol. Sci. 2012, 13(1), 1161-1172; doi:10.3390/ijms13011161
Article

High-Dimensional Descriptor Selection and Computational QSAR Modeling for Antitumor Activity of ARC-111 Analogues Based on Support Vector Regression (SVR)

1,2,†
, 1,†
, 1
, 3
 and 1,2,*
Received: 3 November 2011; in revised form: 9 January 2012 / Accepted: 17 January 2012 / Published: 20 January 2012
View Full-Text   |   Download PDF [183 KB, uploaded 19 June 2014]   |   Browse Figures
Abstract: To design ARC-111 analogues with improved efficiency, we constructed the QSAR of 22 ARC-111 analogues with RPMI8402 tumor cells. First, the optimized support vector regression (SVR) model based on the literature descriptors and the worst descriptor elimination multi-roundly (WDEM) method had similar generalization as the artificial neural network (ANN) model for the test set. Secondly, seven and 11 more effective descriptors out of 2,923 features were selected by the high-dimensional descriptor selection nonlinearly (HDSN) and WDEM method, and the SVR models (SVR3 and SVR4) with these selected descriptors resulted in better evaluation measures and a more precise predictive power for the test set. The interpretability system of better SVR models was further established. Our analysis offers some useful parameters for designing ARC-111 analogues with enhanced antitumor activity.
Keywords: ARC-111 analogues; QSAR; support vector regression; high-dimensional descriptor selection nonlinearly (HDSN) method; worst descriptor elimination multi-roundly (WDEM) method; RPMI8402 ARC-111 analogues; QSAR; support vector regression; high-dimensional descriptor selection nonlinearly (HDSN) method; worst descriptor elimination multi-roundly (WDEM) method; RPMI8402
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Export to BibTeX |
EndNote


MDPI and ACS Style

Zhou, W.; Dai, Z.; Chen, Y.; Wang, H.; Yuan, Z. High-Dimensional Descriptor Selection and Computational QSAR Modeling for Antitumor Activity of ARC-111 Analogues Based on Support Vector Regression (SVR). Int. J. Mol. Sci. 2012, 13, 1161-1172.

AMA Style

Zhou W, Dai Z, Chen Y, Wang H, Yuan Z. High-Dimensional Descriptor Selection and Computational QSAR Modeling for Antitumor Activity of ARC-111 Analogues Based on Support Vector Regression (SVR). International Journal of Molecular Sciences. 2012; 13(1):1161-1172.

Chicago/Turabian Style

Zhou, Wei; Dai, Zhijun; Chen, Yuan; Wang, Haiyan; Yuan, Zheming. 2012. "High-Dimensional Descriptor Selection and Computational QSAR Modeling for Antitumor Activity of ARC-111 Analogues Based on Support Vector Regression (SVR)." Int. J. Mol. Sci. 13, no. 1: 1161-1172.



Int. J. Mol. Sci. EISSN 1422-0067 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert